{"id":"https://openalex.org/W2740561806","doi":"https://doi.org/10.24963/ijcai.2017/248","title":"Improved Strong Worst-case Upper Bounds for MDP Planning","display_name":"Improved Strong Worst-case Upper Bounds for MDP Planning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740561806","doi":"https://doi.org/10.24963/ijcai.2017/248","mag":"2740561806"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/248","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/248","pdf_url":"https://www.ijcai.org/proceedings/2017/0248.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0248.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081592288","display_name":"Anchit Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anchit Gupta","raw_affiliation_strings":["Indian Institute of Technology Bombay","Department of Computer Science and Engineering, Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038200034","display_name":"Shivaram Kalyanakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shivaram Kalyanakrishnan","raw_affiliation_strings":["Indian Institute of Technology Bombay","Department of Computer Science and Engineering, Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081592288"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.2081,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63858023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1788","last_page":"1794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7732698917388916},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.7064418196678162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4969196617603302},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4872978925704956},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.48679301142692566},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.45711469650268555},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4467249810695648},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43063974380493164},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.36847275495529175},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36262747645378113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3213655948638916},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11590221524238586}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7732698917388916},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.7064418196678162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4969196617603302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4872978925704956},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.48679301142692566},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.45711469650268555},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4467249810695648},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43063974380493164},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.36847275495529175},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36262747645378113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3213655948638916},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11590221524238586},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/248","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/248","pdf_url":"https://www.ijcai.org/proceedings/2017/0248.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/248","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/248","pdf_url":"https://www.ijcai.org/proceedings/2017/0248.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740561806.pdf","grobid_xml":"https://content.openalex.org/works/W2740561806.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494380152","https://openalex.org/W1522772123","https://openalex.org/W1928484725","https://openalex.org/W1959989013","https://openalex.org/W1993058867","https://openalex.org/W2028145673","https://openalex.org/W2031259314","https://openalex.org/W2043871262","https://openalex.org/W2098432798","https://openalex.org/W2107924392","https://openalex.org/W2128694402","https://openalex.org/W2152479402","https://openalex.org/W2153460097","https://openalex.org/W2162425318","https://openalex.org/W2255559446","https://openalex.org/W2321292752","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2562620744","https://openalex.org/W2569788251","https://openalex.org/W2575322979","https://openalex.org/W2949533818","https://openalex.org/W2949773717","https://openalex.org/W4229919968","https://openalex.org/W4235295814","https://openalex.org/W4300395467","https://openalex.org/W4300649338","https://openalex.org/W4385965835"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"The":[0,217],"Markov":[1],"Decision":[2],"Problem":[3],"(MDP)":[4],"plays":[5],"a":[6,37,171,182,186,202,211,223,249],"central":[7],"role":[8],"in":[9,74],"AI":[10],"as":[11,86],"an":[12,33,107],"abstraction":[13],"of":[14,24,31,52,65,71,93,106,122,173,189,213,254],"sequential":[15],"decision":[16],"making.":[17],"We":[18],"contribute":[19],"to":[20,96,103,141,150,164,170,225,232,243],"the":[21,29,49,63,69,75,87,91,98,119,158,206,229,233],"theoretical":[22],"analysis":[23],"MDP":[25,53,167],"PLANNING,":[26],"which":[27],"is":[28,180,222],"problem":[30],"computing":[32],"optimal":[34],"policy":[35],"for":[36,136,144,166,228,267],"given":[38],"MDP.":[39,99],"Specifically,":[40],"we":[41,200,220],"furnish":[42],"improved":[43,143],"STRONG":[44],"WORST-CASE":[45],"upper":[46,161,252],"bounds":[47,56,101,135,263],"on":[48,62,82],"running":[50,116,250],"time":[51,251],"planning.":[54],"Strong":[55],"are":[57,149],"those":[58],"that":[59,264],"depend":[60],"only":[61,181],"number":[64,70,92],"states":[66],"n":[67],"and":[68,90,194,209],"actions":[72],"k":[73,127,138,155],"specified":[76],"MDP;":[77],"they":[78],"have":[79,139,265],"no":[80],"dependence":[81],"affiliated":[83],"variables":[84],"such":[85],"discount":[88],"factor":[89],"bits":[94],"needed":[95],"represent":[97],"Worst-case":[100],"apply":[102],"EVERY":[104],"run":[105],"algorithm;":[108],"randomised":[109],"algorithms":[110,174,227,247],"can":[111,239],"typically":[112],"yield":[113],"faster":[114],"EXPECTED":[115],"times.":[117],"While":[118],"special":[120],"case":[121],"2-action":[123,230],"MDPs":[124],"(that":[125],"is,":[126],"=":[128],"2)":[129],"has":[130],"recently":[131],"received":[132],"some":[133],"attention,":[134],"general":[137,152,234],"remained":[140],"be":[142,241],"several":[145,268],"decades.":[146,269],"Our":[147],"contributions":[148],"this":[151,198,237],"case.":[153],"For":[154],">=":[156],"3,":[157],"tightest":[159],"strong":[160],"bound":[162,179,188,212,253],"shown":[163],"date":[165],"planning":[168],"belongs":[169],"family":[172],"called":[175,205],"Policy":[176,245],"Iteration.":[177],"This":[178],"polynomial":[183],"improvement":[184],"over":[185],"trivial":[187],"poly(n,":[190,214,255],"k)":[191,215,256],"k^{n}":[192],"[Mansour":[193],"Singh,":[195],"1999].":[196],"In":[197],"paper,":[199],"generalise":[201],"contrasting":[203],"algorithm":[204],"Fibonacci":[207],"Seesaw,":[208],"derive":[210],"k^{0.6834n}.":[216],"key":[218],"construct":[219],"use":[221],"template":[224],"map":[226],"setting":[231],"setting.":[235],"Interestingly,":[236],"idea":[238],"also":[240],"used":[242],"design":[244],"Iteration":[246],"with":[248],"k^{0.7207n}.":[257],"Both":[258],"our":[259],"results":[260],"improve":[261],"upon":[262],"stood":[266]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}